Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2012 Dec 26;7(12):e50540. doi: 10.1371/journal.pone.0050540

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2012 Chou et al

This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.

PMC Copyright notice

(a) The active imaging volume stored in the global memory is bound with the texture memory. The LOR of a particular direction (red) and its symmetric equivalents corresponding to reflection symmetries in -axis (yellow) and -axis (blue) and interchanged - and -coordinates (green) are shown in the right panel. (b) Each CUDA block contains 128 threads (four warps). These threads multiply the sensitivity functions with the corresponding voxels and store the values in their shared memory for each LOR sequentially. The accumulative summations in the forward projection is performed on the shared memory with parallel reduction summations.

Inline graphic — (a) The active imaging volume stored in the global memory is bound with the texture memory. The LOR of a particular direction (red) and its symmetric equivalents corresponding to reflection symmetries in -axis (yellow) and -axis (blue) and interchanged - and -coordinates (green) are shown in the right panel. (b) Each CUDA block contains 128 threads (four warps). These threads multiply the sensitivity functions with the corresponding voxels and store the values in their shared memory for each LOR sequentially. The accumulative summations in the forward projection is performed on the shared memory with parallel reduction summations.